Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    homicide reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    даги
    0.43
     назем
    0.41
    の話
    0.40
     talks
    0.38
     மா
    0.37
    dataloader
    0.37
    มาจาก
    0.37
    লেখক
    0.36
    Dialogue
    0.36
    നെ
    0.35
    POSITIVE LOGITS
    ㄒ
    0.41
     usp
    0.38
     {}",
    0.36
    汆
    0.36
    <0x00>
    0.36
     scalar
    0.36
     boxing
    0.35
    xyl
    0.35
    عرض
    0.35
    ulloch
    0.35
    Act Density 0.000%

    No Known Activations